IEEE Transactions on Autonomous Mental Development最新文献_第9页

A Spike-Based Model of Neuronal Intrinsic Plasticity 基于峰的神经元内在可塑性模型

IEEE Transactions on Autonomous Mental Development Pub Date : 2013-03-01 DOI: 10.1109/TAMD.2012.2211101

Chunguang Li, Yuke Li

引用次数: 18

Predicting Visual Stimuli From Self-Induced Actions: An Adaptive Model of a Corollary Discharge Circuit 从自我诱导的动作预测视觉刺激:一个自适应的推论放电回路模型

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-12-01 DOI: 10.1109/TAMD.2012.2199989

Jonas Ruesch, R. Ferreira, A. Bernardino

{"title":"Predicting Visual Stimuli From Self-Induced Actions: An Adaptive Model of a Corollary Discharge Circuit","authors":"Jonas Ruesch, R. Ferreira, A. Bernardino","doi":"10.1109/TAMD.2012.2199989","DOIUrl":"https://doi.org/10.1109/TAMD.2012.2199989","url":null,"abstract":"Neural circuits that route motor activity to sensory structures play a fundamental role in perception. Their purpose is to aid basic cognitive processes by integrating knowledge about an organism's actions and to predict the perceptual consequences of those actions. This work develops a biologically inspired model of a visual stimulus prediction circuit and proposes a mathematical formulation for a computational implementation. We consider an agent with a visual sensory area consisting of an unknown rigid configuration of light-sensitive receptive fields which move with respect to the environment and according to a given number of degrees of freedom. From the agent's perspective, every movement induces an initially unknown change to the recorded stimulus. In line with evidence collected from studies on ontogenetic development and the plasticity of neural circuits, the proposed model adapts its structure with respect to experienced stimuli collected during the execution of a set of exploratory actions. We discuss the tendency of the proposed model to organize such that the prediction function is built using a particularly sparse feedforward network which requires a minimum amount of wiring and computational operations. We also observe a dualism between the organization of an intermediate layer of the network and the concept of self-similarity.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"4 1","pages":"290-304"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2012.2199989","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62760831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

A Developmental Approach to Structural Self-Organization in Reservoir Computing 油藏计算中结构自组织的发展方法

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-12-01 DOI: 10.1109/TAMD.2012.2182765

Jun Yin, Y. Meng, Yaochu Jin

{"title":"A Developmental Approach to Structural Self-Organization in Reservoir Computing","authors":"Jun Yin, Y. Meng, Yaochu Jin","doi":"10.1109/TAMD.2012.2182765","DOIUrl":"https://doi.org/10.1109/TAMD.2012.2182765","url":null,"abstract":"Reservoir computing (RC) is a computational framework for neural network based information processing. Little work, however, has been conducted on adapting the structure of the neural reservoir. In this paper, we propose a developmental approach to structural self-organization in reservoir computing. More specifically, a recurrent spiking neural network is adopted for building up the reservoir, whose synaptic and structural plasticity are regulated by a gene regulatory network (GRN). Meanwhile, the expression dynamics of the GRN is directly influenced by the activity of the neurons in the reservoir. We term this proposed model as GRN-regulated self-organizing RC (GRN-SO-RC). Contrary to a randomly initialized and fixed structure used in most existing RC models, the structure of the reservoir in the GRN-SO-RC model is self-organized to adapt to the specific task using the GRN-based mechanism. To evaluate the proposed model, experiments have been conducted on several benchmark problems widely used in RC models, such as memory capacity and nonlinear auto-regressive moving average. In addition, we apply the GRN-SO-RC model to solving complex real-world problems, including speech recognition and human action recognition. Our experimental results on both the benchmark and real-world problems demonstrate that the GRN-SO-RC model is effective and robust in solving different types of problems.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"4 1","pages":"273-289"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2012.2182765","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62760709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 33

Human-Recognizable Robotic Gestures 人类可识别的机器人手势

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-12-01 DOI: 10.1109/TAMD.2012.2208962

J. Cabibihan, W. So, S. Pramanik

引用次数: 45

Model-Free Reinforcement Learning of Impedance Control in Stochastic Environments 随机环境下阻抗控制的无模型强化学习

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-12-01 DOI: 10.1109/TAMD.2012.2205924

F. Stulp, J. Buchli, Alice Ellmer, M. Mistry, Evangelos A. Theodorou, S. Schaal

{"title":"Model-Free Reinforcement Learning of Impedance Control in Stochastic Environments","authors":"F. Stulp, J. Buchli, Alice Ellmer, M. Mistry, Evangelos A. Theodorou, S. Schaal","doi":"10.1109/TAMD.2012.2205924","DOIUrl":"https://doi.org/10.1109/TAMD.2012.2205924","url":null,"abstract":"For humans and robots, variable impedance control is an essential component for ensuring robust and safe physical interaction with the environment. Humans learn to adapt their impedance to specific tasks and environments; a capability which we continually develop and improve until we are well into our twenties. In this article, we reproduce functionally interesting aspects of learning impedance control in humans on a simulated robot platform. As demonstrated in numerous force field tasks, humans combine two strategies to adapt their impedance to perturbations, thereby minimizing position error and energy consumption: 1) if perturbations are unpredictable, subjects increase their impedance through cocontraction; and 2) if perturbations are predictable, subjects learn a feed-forward command to offset the perturbation. We show how a 7-DOF simulated robot demonstrates similar behavior with our model-free reinforcement learning algorithm PI2, by applying deterministic and stochastic force fields to the robot's end-effector. We show the qualitative similarity between the robot and human movements. Our results provide a biologically plausible approach to learning appropriate impedances purely from experience, without requiring a model of either body or environment dynamics. Not requiring models also facilitates autonomous development for robots, as prespecified models cannot be provided for each environment a robot might encounter.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"15 1","pages":"330-341"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2012.2205924","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62761113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 54

Intrinsic Motivation and Introspection in Reinforcement Learning 强化学习中的内在动机与内省

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-12-01 DOI: 10.1109/TAMD.2012.2208457

K. Merrick

{"title":"Intrinsic Motivation and Introspection in Reinforcement Learning","authors":"K. Merrick","doi":"10.1109/TAMD.2012.2208457","DOIUrl":"https://doi.org/10.1109/TAMD.2012.2208457","url":null,"abstract":"Incorporating intrinsic motivation with reinforcement learning can permit agents to independently choose, which skills they will develop, or to change their focus of attention to learn different skills at different times. This implies an autonomous developmental process for skills in which a skill-acquisition goal is first identified, then a skill is learned to solve the goal. The learned skill may then be stored, reused, temporarily ignored or even permanently erased. This paper formalizes the developmental process for skills by proposing a goal-lifecycle using the option framework for motivated reinforcement learning agents. The paper shows how the goal-lifecycle can be used as a basis for designing motivational state-spaces that permit agents to reason introspectively and autonomously about when to learn skills to solve goals, when to activate skills, when to suspend activation of skills or when to delete skills. An algorithm is presented that simultaneously learns: 1) an introspective policy mapping motivational states to decisions that change the agent's motivational state, and 2) multiple option policies mapping sensed states and actions to achieve various domain-specific goals. Two variations of agents using this model are compared to motivated reinforcement learning agents without introspection for controlling non-player characters in a computer game scenario. Results show that agents using introspection can focus their attention on learning more complex skills than agents without introspection. In addition, they can learn these skills more effectively.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"4 1","pages":"315-329"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2012.2208457","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62760796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 21

A Unified Account of Gaze Following 目光跟随的统一描述

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-12-01 DOI: 10.1109/TAMD.2012.2208640

H. Jasso, J. Triesch, G. Deák, J. Lewis

引用次数: 11

Editorial: Impact Factor and Outstanding Paper Awards 编辑:影响因子和杰出论文奖

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-09-10 DOI: 10.1109/TAMD.2012.2211475

Zhengyou Zhang

引用次数: 0

Context-Based Bayesian Intent Recognition 基于上下文的贝叶斯意图识别

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-09-01 DOI: 10.1109/TAMD.2012.2211871

Richard Kelley, A. Tavakkoli, Christopher King, A. Ambardekar, M. Nicolescu, M. Nicolescu

引用次数: 33

Reciprocity and Retaliation in Social Games With Adaptive Agents 基于自适应代理的社交游戏中的互惠和报复

IEEE Transactions on Autonomous Mental Development Pub Date : 2012-09-01 DOI: 10.1109/TAMD.2012.2202658

Derrik E. Asher, Andrew Zaldivar, B. Barton, A. Brewer, J. Krichmar

{"title":"Reciprocity and Retaliation in Social Games With Adaptive Agents","authors":"Derrik E. Asher, Andrew Zaldivar, B. Barton, A. Brewer, J. Krichmar","doi":"10.1109/TAMD.2012.2202658","DOIUrl":"https://doi.org/10.1109/TAMD.2012.2202658","url":null,"abstract":"Game theory has been useful for understanding risk-taking and cooperative behavior. However, in studies of the neural basis of decision-making during games of conflict, subjects typically play against opponents with predetermined strategies. The present study introduces a neurobiologically plausible model of action selection and neuromodulation, which adapts to its opponent's strategy and environmental conditions. The model is based on the assumption that dopaminergic and serotonergic systems track expected rewards and costs, respectively. The model controlled both simulated and robotic agents playing Hawk-Dove and Chicken games against subjects. When playing against an aggressive version of the model, there was a significant shift in the subjects' strategy from Win-Stay-Lose-Shift to Tit-For-Tat. Subjects became retaliatory when confronted with agents that tended towards risky behavior. These results highlight the important interactions between subjects and agents utilizing adaptive behavior. Moreover, they reveal neuromodulatory mechanisms that give rise to cooperative and competitive behaviors.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"4 1","pages":"226-238"},"PeriodicalIF":0.0,"publicationDate":"2012-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2012.2202658","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62761003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 22